1
Selective Safety Steering via Value-Filtered Decoding
提出选择性安全引导方法，通过价值过滤解码提升LLM安全性
arXiv:2605.14746v2 Announce Type: replace Abstract: While large language models (LLMs) are trained to align with human values, their generations may s…
提出选择性安全引导方法，通过价值过滤解码提升LLM安全性
arXiv:2605.14746v2 Announce Type: replace Abstract: While large language models (LLMs) are trained to align with human values, their generations may s…